metadata
language:
- ta
license: apache-2.0
base_model: openai/whisper-medium
tags:
- hf-asr-leaderboard
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_11_0
metrics:
- wer
model-index:
- name: Whisper Medium ta - tamil
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: Common Voice 11.0
type: mozilla-foundation/common_voice_11_0
config: ta
split: None
args: 'config: ta, split: test'
metrics:
- name: Wer
type: wer
value: 46.70043811610077
Whisper Medium ta - tamil
This model is a fine-tuned version of openai/whisper-medium on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.4126
- Wer: 46.7004
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 4000
Training results
Training Loss | Epoch | Step | Validation Loss | Wer |
---|---|---|---|---|
0.1445 | 1.6807 | 1000 | 0.2832 | 51.7798 |
0.0281 | 3.3613 | 2000 | 0.3271 | 49.2744 |
0.003 | 5.0420 | 3000 | 0.3818 | 47.0701 |
0.0011 | 6.7227 | 4000 | 0.4126 | 46.7004 |
Framework versions
- Transformers 4.42.0.dev0
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1